Skip to main content

Nowcasting Earthquakes by Visualizing the Earthquake Cycle with Machine Learning: A Comparison of Two Methods

Abstract

The earthquake cycle of stress accumulation and release is associated with the elastic rebound hypothesis proposed by H.F. Reid following the M7.9 San Francisco earthquake of 1906. However, observing details of the actual values of time- and space-dependent tectonic stress is not possible at the present time. In two previous papers, we have proposed methods to image the earthquake cycle in California by means of proxy variables. These variables are based on correlations in patterns of small earthquakes that occur nearly continuously in time. The purpose of the present paper is to compare these two methods by evaluating their information content using decision thresholds and Receiver Operating Characteristic methods together with Shannon information entropy. Using seismic data from 1940 to present in California, we find that both methods provide nearly equivalent information on the rise and fall of earthquake correlations associated with major earthquakes in the region. We conclude that the resulting timeseries can be viewed as proxies for the cycle of stress accumulation and release associated with major tectonic activity.

Article Highlights

  • The current state of the earthquake cycle of tectonic stress accumulation and release is unobservable

  • We review two methods for visualizing the current state of the earthquake cycle from correlation in small earthquake patterns

  • Machine learning techniques indicate that signals in a correlation time series corresponding to future large earthquakes can be detected

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Notes

  1. 1.

    https://earthquake.usgs.gov/earthquakes/search/.

  2. 2.

    https://machinelearningmastery.com/random-forest-for-time-series-forecasting/.

References

  1. Bowman DE, Ouillon G, Sammis CG, Sornette A, Sornette D (1998) An observational test of the critical earthquake concept. J Geophys Res 103(10):24359–24372. https://doi.org/10.1029/98JB00792

    Article  Google Scholar 

  2. Green DM, Swets JA (1966) Signal detection theory and psychophysics. Wiley, New York, NY

    Google Scholar 

  3. Hill DP, Prejean SG (2007) Dynamic triggering, in Earthquake seismology. In: Schubert G, Kanamori H (eds) Treatise on Geophysics (vol 4, pp 257–291), Schubert, G (Editor-in Chief) (Elsevier, Amsterdam)

  4. Holliday JR, Rundle JB, Tiampo KF, Donnellan A (2006) Systematic procedural and sensitivity analysis of pattern informatics method for forecasting large (M>5) earthquake events in southern California. Pure Appl Geophys 163(11):2433–2454

    Article  Google Scholar 

  5. Holliday JR, Turcotte DL, Rundle JB (2008) Self-similar branching of aftershock sequences. Phys A 387:933–943

    Article  Google Scholar 

  6. Holliday JR, Rundle JB, Turcotte DL, Klein W, Tiampo KF (2006) Space-time correlation and clustering of major earthquakes. Phys Rev Lett 97:238501

    Article  Google Scholar 

  7. Holliday JR, Chen CC, Tiampo KF, Rundle JB, Turcotte DL, Donnellan A (2007) A RELM earthquake forecast based on pattern informatics. Seism Res Lett 78:87–93

    Article  Google Scholar 

  8. Joy JE, Penhoet EE, Petitti DB (eds) (2005) Benefits and limitations of mammography. In: Saving women's lives: strategies for improving breast cancer detection and diagnosis. In: Institute of Medicine (US) and National Research Council (US) Committee on New Approaches to Early Detection and Diagnosis of Breast Cancer. Washington (DC): National Academies Press (US)

  9. Kucherov L, Ryvkin M (2014) Fracture toughness of open-cell Kelvin foam. Int J Solids Struct 51(2):440–448

    Article  Google Scholar 

  10. Lee YT, Turcotte DL, Holliday JR, Sachs MK, Rundle JB, Chen CC, Tiampo KF (2011) Results of the Regional Earthquake Likelihood Models (RELM) test of earthquake forecasts in California. Proc Nat Acad Sci USA 108:16533–16538. https://doi.org/10.1073/pnas.1113481108

    Article  Google Scholar 

  11. Luginbuhl M, Rundle JB, Turcotte DL (2018a) Natural time and nowcasting earthquakes: are large global earthquakes temporally clustered? Pure Appl Geophys 175:661–670

    Article  Google Scholar 

  12. Luginbuhl M, Rundle JB, Turcotte DL (2018b) Natural time and nowcasting induced seismicity at the Groningen gas field in the Netherlands. Geophys J Int 215:753–759

    Article  Google Scholar 

  13. Luginbuhl M, Rundle JB, Hawkins A, Turcotte DL (2018c) Nowcasting earthquakes: a comparison of induced earthquakes in Oklahoma and at the geysers, California. Pure Appl Geophys 175(1):49–65

    Article  Google Scholar 

  14. Luginbuhl M, Rundle JB, Turcotte DL (2019) Natural time and nowcasting earthquakes: are large global earthquakes temporally clustered? In: Williams C, Peng Z, Zhang Y, Fukuyama E, Goebel T, Yoder M (eds) Earthquakes and multi-hazards around the Pacific Rim, Vol. II. PAGEOPH topical volumes. Birkhäuser, Cham

    Google Scholar 

  15. Nanjo KZ (2020) Were changes in stress state responsible for the 2019 Ridgecrest, California, earthquakes? Nature communications. https://doi.org/10.1038/s41467-020-16867-5

    Article  Google Scholar 

  16. Olami Z, Feder HJS, Christensen K (1992) Self organized criticality in a continuous non-conservative cellular automaton modeling earthquakes. Phys Rev Lett 68:1244–1247

    Article  Google Scholar 

  17. Omori F (1894) On the after-shocks of earthquakes. J Coll Sci Imp Univ Tokyo 7:111–200

  18. Pasari S (2019a) Nowcasting earthquakes in the Bay-of-Bengal region. Pure Appl Geophys 23:537–559

    Google Scholar 

  19. Pasari S (2019b) Nowcasting earthquakes in the Bay of Bengal Region. Pure Appl Geophys 176:1417. https://doi.org/10.1007/s00024-018-2037-0

    Article  Google Scholar 

  20. Pasari S (2020) Stochastic Modeling of Earthquake Interevent Counts (Natural Times) in Northwest Himalaya and Adjoining Regions. Mathematical Modeling and Computational Tools: ICACM 2018, Kharagpur, India, November 23–25 320:495

  21. Pasari S, Mehta A (2018) Nowcasting earthquakes in the northwest Himalaya and surrounding regions. Int Arch Photogramm Remote Sens Spatial Inf Sci XLII–5:855–859

    Article  Google Scholar 

  22. Pasari S, Sharma Y (2020) Contemporary earthquake hazards in the West-Northwest Himalaya: a statistical perspective through natural times. Seismol Soc Am 91.6 (2020):3358–3369

  23. Peresan A, Gentili S (2018) Seismic clusters analysis in Northeastern Italy by the nearest-neighbor approach. Phys Earth Planet Inter 274:87–104

    Article  Google Scholar 

  24. Perez-Oregon J, Angulo-Brown F, Sarlis NV (2020) Nowcasting avalanches as earthquakes and the predictability of strong avalanches in the Olami-Feder-Christensen Model. Entropy 22(11):1228

    Article  Google Scholar 

  25. Reinhart A (2015) Statistics done wrong: the woefully complete guide. No starch press, San Francisco

    Google Scholar 

  26. Richter CF (1958) Elementary Seismology, W.H Freeman, San Francisco, pp 768

  27. Rouet-Leduc B, Hulbert C, Johnson PA (2019) Continuous chatter of the Cascadia subduction zone revealed by machine learning. Nat Geosci 12:75–79

    Article  Google Scholar 

  28. Rouet-Leduc B, Hulbert C, Lubbers N, Barros K, Humphreys CJ, Johnson PA (2017) Machine learning predicts laboratory earthquakes. Geophys Res Lett. https://doi.org/10.1002/2017GL074677

    Article  Google Scholar 

  29. Rundle JB, Jackson DD (1977) Numerical simulation of earthquake sequences. Bull Seismol Soc Am 67(5):1363–1377

    Google Scholar 

  30. Rundle JB, Donnellan A (2020) Nowcasting earthquakes in Southern California with machine learning: bursts, swarms, and aftershocks may be related to levels of regional tectonic stress. Earth Sp Sci. https://doi.org/10.1029/2020EA001097

    Article  Google Scholar 

  31. Rundle JB, Tiampo KF, Klein W, Martins JSS (2002) Self-organization in leaky threshold systems: the influence of near mean field dynamics and its implications for earthquakes, neurobiology and forecasting. Proc Nat Acad Sci USA 99(Supplement 1):2514–2521

    Article  Google Scholar 

  32. Rundle JB, Luginbuhl M, Giguere A, Turcotte DL (2018) Natural time, nowcasting and the physics of earthquakes: estimation of risk to global megacities. Pure Appl Geophys 175:647–660

    Article  Google Scholar 

  33. Rundle JB, Turcotte DL, Sammis C, Klein W, Shcherbakov R (2003) Statistical physics approach to understanding the multiscale dynamics of earthquake fault systems (invited). Rev Geophys Space Phys. https://doi.org/10.1029/2003RG000135

    Article  Google Scholar 

  34. Rundle JB, Giguere A, Turcotte DL, Crutchfield JP, Donnellan A (2019a) Global seismic nowcasting with Shannon information entropy. Earth Sp Sci 6:456–472

    Google Scholar 

  35. Rundle JB, Turcotte DL, Donnellan A, GrantLudwig L, Luginbuhl M, Gong G (2016b) Nowcasting earthquakes. Earth Sp Sci 3:480–486. https://doi.org/10.1002/2016EA000185

    Article  Google Scholar 

  36. Rundle JB, Donnellan A, Fox GCF, Crutchfield JP, Granat R (2021a) Nowcasting earthquakes: imaging the earthquake cycle in California with machine learning, submitted to Earth and space Science

  37. Rundle JB, Stein S, Donnellan A, Turcotte DL, Klein W, Saylor C (2021b) The complex dynamics of earthquake fault systems: new approaches to forecasting and nowcasting of earthquakes. Rep Prog Phys 84:076801

  38. Sarlis NV, Skordas ES, Varotsos PA (2018) A remarkable change of the entropy of seismicity in natural time under time reversal before the super-giant M9 Tohoku earthquake on 11 March 2011. EPL. https://doi.org/10.1209/0295-5075/124/29001

    Article  Google Scholar 

  39. Sarlis NV et al (2013) Minimum of the order parameter fluctuations of seismicity before major earthquakes in Japan. Proc Natl Acad Sci 110(34):13734–13738

    Article  Google Scholar 

  40. Sayers CM, Calvez JL (2010) Characterization of microseismic data in gas shales using the radius of gyration tensor. In: SEG Technical Program Expanded Abstracts. Society of Exploration Geophysicists, pp 2080–2084.

  41. Scholz CH (2019) The mechanics of earthquakes and faulting. Cambridge University Press

  42. Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(4):623–656

    Article  Google Scholar 

  43. Shcherbakov R, Turcotte DL, Rundle JB (2005a) Aftershock statistics. Pure Appl Geophys 162(6–7):1051–1076. https://doi.org/10.1007/s00024-004-2661-8

    Article  Google Scholar 

  44. Shcherbakov R, Turcotte DL, Rundle JB (2005) Aftershock statistics. Pure Appl Geophys 162(6–7):1051–1076. https://doi.org/10.1007/s00024-004-2661-8

    Article  Google Scholar 

  45. Stauffer D, Aharony A (2018) Introduction to percolation theory. CRC press

  46. Tiampo KF, Rundle JB, Gross SJ, McGinnis S, Klein W (2002a) Eigenpatterns in southern California seismicity. J Geophys Res 107(B12):2354

    Article  Google Scholar 

  47. Tiampo KF, Rundle JB, McGinnis SA, Klein W (2002b) Pattern dynamics and forecast methods in seismically active regions. Pure Appl Geophys 159:2429–2467

    Article  Google Scholar 

  48. Tiampo KF, Rundle JB, McGinnis S, Gross S, Klein W (2002c) Mean field threshold systems and phase dynamics: an application to earthquake fault systems. Europhys. Lett. 60:481–487

    Article  Google Scholar 

  49. Tullis TE, Richards-Dinger K, Barall M, Dieterich JH, Field EH, Heien EM, Kellogg LH, Pollitz FF, Rundle JB, Sachs MK, Turcotte DL, Ward SN, Yikilmaz MB (2012) Generic earthquake simulator. Seismol Res Lett 83:959–963

    Article  Google Scholar 

  50. Varotsos P, Sarlis NV, Skordas ES (2001) Spatiotemporal complexity aspects on the interrelation between Seismic Electric Signals and seismicity. Practica Athens Acad 76:294–321

    Google Scholar 

  51. Varotsos P, Sarlis NV, Skordas ES (2011a) Natural time analysis: the new view of time. Precursory Seismic Electric Signals, Earthquakes and other Complex Time-Series. Springer-Verlag, Berlin Heidelberg

  52. Varotsos PA, Sarlis NV, Skordas ES (2011b) Scale-specific order parameter fluctuations of seismicity in natural time before mainshocks. EPL (europhysics Letters) 96(5):59002

    Article  Google Scholar 

  53. Varotsos P, Sarlis NV, Skordas ES (2014) Study of the temporal correlations in the magnitude time series before major earthquakes in Japan. J Geophys Res Space Phys 119:9192–9206

    Article  Google Scholar 

  54. Varotsos P, Sarlis NV, Skordas ES, Lazaridou MS (2013) Seismic Electric Signals: An additional fact showing their physical interconnection with seismicity. Tectonophys 589:116–125

    Article  Google Scholar 

  55. Varotsos P, Sarlis NV, Skordas ES (2002) Long-range correlations in the electric signals that precede rupture. Phys Rev E 66.1:011902

  56. Varotsos PA, Sarlis NV, Skordas ES (2012) Remarkable changes in the distribution of the order parameter of seismicity before mainshocks. EPL 100(3):39002

    Article  Google Scholar 

  57. Varotsos PA, Sarlis NV, Skordas ES (2020a) Self-organized criticality and earthquake predictability: a long-standing question in the light of natural time analysis. EPL 132(2):29001

    Article  Google Scholar 

  58. Varotsos PA, Skordas ES, Sarlis NV (2020) Fluctuations of the entropy change under time reversal: further investigations on identifying the occurrence time of an impending major earthquake. EPL. https://doi.org/10.1209/0295-5075/130/29001

    Article  Google Scholar 

  59. Zaliapin I, Ben-Zion Y (2016a) A global classification and characterization of earthquake clusters. Geophys J Intl 207(1):608–634

    Article  Google Scholar 

  60. Zaliapin I, Ben-Zion Y (2016b) Discriminating characteristics of tectonic and human-induced seismicity. Bull Seismol Soc Am 106(3):846–859

    Article  Google Scholar 

Download references

Acknowledgements

The research of JBR was supported in part by NASA grant (NNX17AI32G) to UC Davis (nowcasting) and in part by DOE grant (DOE DE-SC0017324) to UC Davis (data analysis). Portions of the research by Andrea Donnellan were carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration. The research by JPC was supported by DOE grant (DOE DE-SC0017324) to UC Davis. None of the authors has identified financial conflicts of interest. We thank colleagues including Donald Turcotte for helpful discussions. The data used in this paper were downloaded from the online earthquake catalog1 maintained by the US Geological Survey, accessed on December, 31, 2020. This research was also supported in part by the Southern California Earthquake Center (Contribution No. 10929). SCEC is funded by NSF Cooperative Agreement EAR-1600087 & USGS Cooperative Agreement G17AC00047.

Author information

Affiliations

Authors

Corresponding author

Correspondence to John B. Rundle.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Rundle, J.B., Donnellan, A., Fox, G. et al. Nowcasting Earthquakes by Visualizing the Earthquake Cycle with Machine Learning: A Comparison of Two Methods. Surv Geophys (2021). https://doi.org/10.1007/s10712-021-09655-3

Download citation

Keywords

  • Nowcasting
  • Earthquakes
  • Machine learning
  • Information